Retell 使用 OpenAI 模型来帮助提供100M 月通电源
GPT‐6 阿斯特拉超过 Retell的声音是agent 基准测试，而Codex则帮助它达到每个雇员1.6M的年收入运行率。
100M+
每月接听电话
80%+
客户解决率
1万亿
消耗的 OpenAI 令牌
$1.6M
每名雇员的年收入率
Retell AI(在新窗口中打开)是一个用于联系中心操作的语音AI平台，帮助企业建设agents，可以回答问题，采取行动，并在需要时将呼叫者与个人连接。 其平台目前服务于4000多家企业，每月的呼叫量从2026年初的3000万增长到9月的一亿多。
由于Retell服务于更多工作流程复杂的企业，它使用OpenAI模型保持调用质量和可靠性高。 如今，OpenAI模型对雷特尔80%的呼叫产生响应，客户实现解析率超过80%. Retell也超过了OpenAI模型所消耗的一万亿令牌，反映了这种采用的规模。
Retell的工程师在整个开发过程中都使用Codex，从研究不熟悉的代码到建筑特性和调试问题，以及GPT‐6 Astra测试前端接口。
“我们选择的模式是客户选择销售商的方式：在真正的电话中，而不是演示。 OpenAI一直在赚取地盘。”
企业之声agents需要遵循公司政策并保持其分配的角色，即使随着对话的改变。 雷特尔构建了它的vCX 基准测试，用从真实生产情景中抽取的艰难多回合对话来比较数十个模型。
它测试模型遵循指示的好坏程度，坚持以它们获得的信息为基础，调用正确的工具，并使用自然对话语言。 在雷特尔的2026年10月13日的"基准测试"中，GPT‐6 Astra以89.7%的成绩排名第一。
Retelll还分享了在GPT‐6的发布前进行的评价，该评价显示，GPT‐5.5在非卤化率(88.0%)和工具调用正确性(88.3%)这两个模型中，在两个措施上都表现优于Gemini‐3.1-Pro和Claude‐4.6。 也导致了非卤化率与推理。
选择OpenAI模型的Retell 称新客户继续使用。 客户还可以通过实时API和OpenAI 文本转语音作为语音引擎访问OpenAI实时模型。 Retell使新的OpenAI模型在发布的当天就可用，并随着模型的改进而重新运行了它的基准测试。
联系中心团队使用Retell来定义他们的agents的商业背景，目标和规则。 开发者可以进一步配置工作流程和集成。
在电话中，Retell 的用具会运行音频模型，跟踪对话，OpenAI型号，包括：GPT‐6.1 Sol,GPT‐6 Astra，和GPT‐5.5，使用客户的指示和谈话上下文生成响应和请求工具呼叫。 Retell通过与客户系统的整合执行这些呼叫，并可将结果写回客户记录。
当需要人类判断时，语音agent会用上下文向代表作简报，回答他们的后续问题，并在连接客户之前确认他们已经准备好。 在打完电话后，雷特尔使用GPT‐5.6 Terra分析记录并提取结果和其他数据。
通过这种方法，雷特尔报告客户解析率超过80%. 在Anker电子公司，agents在美国和英国处理Tier‐1售后支持，包括订单跟踪、保修检查和故障排除。 Anker报告了80.4%的破案率和63个净促进者分数。 其团队也以称 agents为基调，节奏和温暖达到了他们期望的人类agent的标准。
在Pine Park Health, Retell agents处理预约提醒和主动安排，并将结果记录在病人的医疗图上。 该小组恢复了相当于2.1个全职角色的医疗助理时间，并将其转用于病人护理。 其行程agent在到达患者时实现了55.7%的预订率。
Retell 平台的日间流量可达一夜之间低点的50多倍。 为了帮助即使在高峰需求时也保持呼叫响应，雷特尔使用专用服务器与OpenAI，共享于它的客户。 在雷特尔的2026年10月13日的基准测试，GPT‐6 Astra和GPT‐6中。 索尔每个记录了883毫秒的一等刑期中位数，而克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克克
OpenAI的区域API端点允许开发者将交通线路通向特定的地理区域，这有助于Retell减少网络出行时间并满足客户在保健和金融服务等行业的数据居住要求。
Retell还将冗余建入服务的每一层。 它运行自己的电话堆，第二堆可以接管，还有语音和模型服务的备份，在服务失败时帮助保持通话运行。
随着雷特尔的企业成长带来对自定义工作流程和集成的更多请求，其工程师往往需要在不熟悉的代码库部分工作。 在写出代码之前，他们给"Codex"一个高级要求。 Codex调查代码，对照实际数据加以检查，并解释需要改变什么。 一位工程师称 Codex的研究工作比他做得更好，更快。
在执行期间，工程师说Codex常常捕捉到他们没有考虑过的细节。 对于调试，Codex 交叉引用日志和数据库记录与代码，以调查正在发生的事情。 Retell的工程师在与基于OpenAI模型的客户合作时，也使用Codex来加快任务，例如编写指导模型如何在客户应用中响应的指令。
为了测试其网页界面的变化，雷特尔依赖于GPT‐6 Astra的计算机使用。 当工程师打开前端拉力请求时，GPT‐6 Astra打开了界面，点击通过它，测试流出，试图打破它们，并报告它发现的问题。 Retell 称早期的模型无法可靠地完成这项工作。
Retell继续雇佣员工，Retell报告，每个雇员的年收入为160万美元。
“通过使用Codex，工程队有一个虚拟的队友，他们可以在任何困难的任务上与他们配对。”
各行各业悉能出其想为所行客户。 Retell的目标是让最接近该作品的人们直接应用他们的专业知识，使用高级语音AI和一个让他们建立，测试，改善自己agents的平台。 其次，雷特尔计划扩大质量保证和模拟，支持更多的语言，并开发知识库自动学习。
随着OpenAI型号的不断推进，雷特尔预计其客户会以自己的条件向数百万来电者提供世界一流的服务。
" 没有人比公司本身更了解公司的客户。 我们赋予他们根据这种专门知识采取行动的权力，并直接改进AI agents. 目标是他们建立一个内部部署的工程师团队，他们拥有并管理全部工程，"称 Bing.
本文由 AI宝库自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
Retell uses OpenAI models to help power 100M monthly calls
GPT‑6 Astra tops Retell’s voice agent benchmark, while Codex helps it reach a $1.6M annual revenue run rate per employee.
100M+
Monthly calls handled
80%+
Customer resolution rates
1 trillion
OpenAI tokens consumed
$1.6M
Annual revenue run rate per employee
Retell AI(opens in a new window) is a voice AI platform for contact center operations, helping businesses build agents that can answer questions, take action, and connect a caller with a person when needed. Its platform now serves more than 4,000 businesses, with monthly call volume growing from 30 million in early 2026 to more than 100 million by September.
As Retell serves more enterprises with complex workflows, it uses OpenAI models to keep call quality and reliability high. Today, OpenAI models generate responses for 80% of calls on Retell, with customers achieving resolution rates above 80%. Retell has also surpassed 1 trillion tokens consumed across OpenAI models, reflecting the scale of that adoption.
Retell’s engineers use Codex throughout development, from researching unfamiliar code to building features and debugging issues, and GPT‑6 Astra to test front-end interfaces.
“We choose models the way our customers choose vendors: on real calls, not demos. OpenAI keeps earning its spot.”
Enterprise voice agents need to follow company policies and stay within their assigned roles, even as conversations change. Retell built its vCX benchmark to compare dozens of models using difficult, multi-turn conversations drawn from real production scenarios.
It tests how well models follow instructions, stay grounded in the information they are given, call the right tools, and use natural conversational language. In Retell’s October 13, 2026 benchmark, GPT‑6 Astra ranked first for instruction following at 89.7%.
Retell also shared evaluations conducted before the launch of the GPT‑6 Astra model that showed GPT‑5.5 ranking highest among models on both non-hallucination rate (88.0%) and tool-call correctness (88.3%) with reasoning enabled, outperforming Gemini‑3.1‑Pro and Claude‑4.6 on both measures. It also led on non-hallucination rate with reasoning off.
Retell says new customers who choose OpenAI models continue using them. Customers also have access to OpenAI Realtime models through the Realtime API and OpenAI text-to-speech as a voice engine. Retell makes new OpenAI models available the day they launch and reruns its benchmark as models improve.
Contact center teams use Retell to define their agents’ business context, goals, and rules. Developers can further configure workflows and integrations.
During a call, Retell’s harness runs the audio models, tracks the conversation, and manages when the agent speaks, listens, or responds to interruptions. OpenAI models, including GPT‑6.1 Sol, GPT‑6 Astra, and GPT‑5.5, use the customer’s instructions and conversation context to generate responses and request tool calls. Retell executes those calls through integrations with the customer’s systems and can write outcomes back to a customer record.
When human judgment is needed, the voice agent briefs the representative with context, answers their follow-up questions, and confirms they are ready before connecting the customer. After a call, Retell uses GPT‑5.6 Terra to analyze the transcript and extract outcomes and other data.
With this approach, Retell reports customer resolution rates above 80%. At electronics company Anker, agents handle Tier‑1 post-sales support in the US and UK, including order tracking, warranty checks, and troubleshooting. Anker reported an 80.4% case resolution rate and a Net Promoter Score (NPS) of 63. Its team also said the agents’ tone, pacing, and warmth met the standard they expected of a human agent.
At Pine Park Health, Retell agents handle appointment reminders and proactive scheduling and record the outcomes in patients’ medical charts. The team recovered medical-assistant time equivalent to 2.1 full-time roles and redirected it to patient care. Its scheduling agent achieved a 55.7% booking rate when it reached a patient.
Daytime traffic on Retell’s platform can reach more than 50 times its overnight low. To help keep calls responsive even at peak demand, Retell uses dedicated servers with OpenAI, shared across its customers. In Retell’s October 13, 2026 benchmark, GPT‑6 Astra and GPT‑6 Sol each recorded median first-sentence latency of 883 milliseconds, with GPT‑5.6 Luna ranking highest at 497 milliseconds.
OpenAI’s regional API endpoints allow developers to route traffic to specific geographic regions, which helps Retell reduce network travel time and meet customers’ data residency requirements in industries such as healthcare and financial services.
Retell also builds redundancy into each layer of the service. It runs its own telephony stack with a second stack ready to take over, along with backups for voice and model services, to help keep calls running when a service fails.
As Retell’s enterprise growth brings more requests for custom workflows and integrations, its engineers often need to work in unfamiliar parts of the codebase. Before writing code, they give Codex a high-level requirement. Codex surveys the code, checks it against actual data, and explains what needs to change. One engineer said Codex did this research better and much faster than he could.
During implementation, engineers say Codex often catches details they had not considered. For debugging, Codex cross-references logs and database records with the code to investigate what is happening. Retell’s engineers also use Codex in their work with customers building on OpenAI models to speed up tasks such as writing the instructions that guide how a model responds in a customer’s application.
To test changes to its web interface, Retell relies on GPT‑6 Astra’s computer use. When an engineer opens a front-end pull request, GPT‑6 Astra opens the interface, clicks through it, tests flows, tries to break them, and reports the issues it finds. Retell says earlier models could not perform this work reliably.
Retell continues to hire, but its engineering team hasn’t needed to grow at the same pace as the business. Retell reports $1.6 million in annual revenue run rate per employee.
“By using Codex, the engineering team has a virtual teammate that can pair with them on any kind of difficult task.”
Every business knows how it wants to serve its customers. Retell’s goal is to let the people closest to that work apply their expertise directly, using advanced voice AI and a platform that lets them build, test, and improve their own agents. Next, Retell plans to expand quality assurance and simulation, support more languages, and develop knowledge base auto-learning.
As OpenAI models continue to advance, Retell expects its customers to deliver world-class service to millions of callers, on their own terms.
“No one knows a company’s customers better than the company itself. We give them the power to act on that expertise and improve AI agents directly. The goal is for them to build an in-house team of internally deployed engineers who own and run it all,” says Bing.
Auto-fetched and translated by AI Gem Box. All rights belong to the original author.